from diffusers import StableDiffusionPipeline
import torch

pipe = StableDiffusionPipeline.from_pretrained("ErasureResearch/uce_airliner", torch_dtype=torch.float16).to("cuda")
prompt = "a photo of a airliner"
image = pipe(prompt).images[0]
image.save("erased_airliner.png")

Citation

If you use this model in your research, please cite:

bibtex

@article{concept_erasure_2024,
  title={Concept Erasure in Diffusion Models},
  author={ErasureResearch Team},
  journal={Proceedings of...},
  year={2024}
}